Output Loop Bench · Reasoning
Prospection challenge: AI models compared
Insight from the prospection database, the same questions each run. 9 models tested on the same task.
Yes/no facts per business
544 local trade businesses (landscapers, electricians, removal companies, roofers, drainage companies and plumbers) from the original research. Each decision model answers seven yes/no questions about every business, and the Lab adds the answers up. The top row is the correct answer, computed from the same rules, so every miss shows as a difference.
| Model | Maker | Time | Tokens |
|---|---|---|---|
| Jev | TypeSafe | 38.7s | 1,740,547 |
| Perplexity Decisions | Perplexity | 77.4s | 1,603,663 |
| gemini-4-argon-medium | 421.5s | 508,490 | |
| kimi-k3-max | Moonshot (Kimi) | 480.5s | 543,606 |
| claude-haiku-5-5 | Anthropic | 660.5s | 2,748,961 |
| Clef | Other | 793.6s | 572,825 |
| gpt-6-luna | OpenAI | 875.2s | 520,444 |
| glm-5.3 | Z.ai | 1108.6s | 565,868 |
| qwen3.8-flash | Alibaba (Qwen) | 1395.4s | 611,740 |